Update docs

docs/examples/basicusage.md

@@ -1,4 +1,4 @@
-scDEF takes as input an [AnnData](https://anndata.readthedocs.io/en/latest/) object containing UMI counts. We strongly recommend filtering the data to keep only highly variable genes. After [installing scDEF](https://cbg-ethz.github.io/scDEF/installation), the basic usage is to import it:
+scDEF takes as input an [AnnData](https://anndata.readthedocs.io/en/latest/) object containing UMI counts. We strongly recommend filtering the data to keep only highly variable genes. With scDEF [installed](https://cbg-ethz.github.io/scDEF/installation), start by importing the module:
 
 ```
 import scdef

docs/index.md

@@ -8,3 +8,30 @@
 [![docs](https://github.com/cbg-ethz/scDEF/actions/workflows/docs.yaml/badge.svg)](https://cbg-ethz.github.io/scDEF/)
 
 Deep exponential families for single-cell data. scDEF learns hierarchies of cell states and their gene signatures from scRNA-seq data. The method can be used for dimensionality reduction, visualization, gene signature identification, clustering at multiple levels of resolution, and batch integration. The informed version (iscDEF) can additionally take known gene lists to jointly assign cells to types and find clusters within each type.
+
+## Installation
+scDEF is available through [PyPI](https://pypi.org/project/scdef):
+
+```
+pip install scdef
+```
+
+Please be sure to install a version of [JAX](https://jax.readthedocs.io/) that is compatible with your GPU (if applicable). scDEF is much faster on the GPU than on the CPU.
+
+### Optional: using the `scdef.benchmark` module
+The `scdef.benchmark` module includes wrapper functions to other methods. If you wish to use it, please install the extras:
+
+```
+pip install scdef[extras]
+```
+
+The `scdef.benchmark` also contains a wrapper function to `scVI` from [scvi-tools](https://scvi-tools.org/), but `scvi-tools` is not included in the extras and it must be installed separately if you wish to use it. The same applies to [scHPF](https://github.com/simslab/scHPF).
+
+## Example notebooks
+To get started with scDEF, please see the example notebooks:
+
+- [Introduction to scDEF on 3k PBMCs](http://cbg-ethz.github.io/scDEF/examples/scdef-pbmcs3k/)
+
+
+## Contributors
+Pedro Falé Ferreira [@pedrofale](https://github.com/pedrofale)

mkdocs.yaml

@@ -13,7 +13,18 @@ theme:
     - content.code.copy
   language: en
   palette:
-    primary: darkpurple
+    - scheme: default
+      toggle:
+        icon: material/toggle-switch-off-outline
+        name: Switch to dark mode
+      primary: indigo
+    - scheme: slate
+      toggle:
+        icon: material/toggle-switch
+        name: Switch to light mode
+      primary: indigo
+  favicon: assets/images/icon.svg
+  logo: assets/images/icon.svg
 
 
 plugins:
@@ -29,9 +40,7 @@ plugins:
             show_root_heading: true
 
 nav:
-  - Getting started:
-    - Introduction: index.md
-    - Installation: installation.md
+  - Getting started: index.md
   - Examples:
     - Basic usage: examples/basicusage.md
     - Getting started with 3k PBMCs: examples/scdef-pbmcs3k.ipynb

scdef/models/_iscdef.py

@@ -14,6 +14,7 @@ class iscDEF(scDEF):
     This model extends the basic scDEF by using gene sets to guide the factors.
     iscDEF can either set the given sets as top layer factors and learn higher-resolution
     structure, or use them as the lowest resolution and learn a hierarchy that relates them.
+    All the methods from scDEF are available in iscDEF.
 
     Args:
         adata: AnnData object containing the gene expression data. scDEF learns a model from